quantization — Shrinking a model by storing its numbers less precisely — like rounding — so it runs faster and fits on smaller hardware, at a small quality cost.
Why it matters
FP4 quantizationShrinking a model by storing its numbers less precisely — like rounding — so it runs faster and fits on smaller hardware, at a small quality cost.Full definition → brings FLUX.1 [dev] down to 10GB VRAM while roughly doubling throughput on Blackwell RTX cards, changing what image generation is practical to run locally rather than via API.
